An Intelligent Vision System for Detecting Defects in Micro-Armatures for Smartphones

Abstract

Automatic vision inspection technology shows a high potential for quality inspection, and has drawn great interest in micro-armature manufacturing. Given that the inspection process is highly influenced by the lack of real standardization and efficiency performed with the human eye, thus, it is necessary to develop an automatic defect detection process. In this work, an elaborated vision system for the defect inspection of micro-armatures used in smartphones was developed. It consists of two parts, the front-end module and the deep convolution neural networks (DCNNs) module, which are responsible for different areas. The front-end module runs first and the DCNNs module will not run if the output of the front-end module is negative. To verify the application of this system, an apparatus consisting of an objective table, control panel, and a camera connected to a Personal Computer (PC) was used to simulate an industrial position of production. The results indicate that the developed vision system is capable of defect detection of micro-armatures.Recently, deep convolutional neural networks (DCNNs) have been proved to be important methods in visual detection. However, some classical methods should still be considered. Literature [6] mentioned above is an example. For instance, in order to get better parameters, a suitable smart manufacturing strategy for real industrial conditions was proposed. The results of this dataset showed that the Adaboost ensembles provided the highest accuracy and were more easily optimized than ANNs [7]. Obviously, for now, there are some limitations with using classical methods alone or using DCNNs directly. For classical methods, for example, they usually come with high complexity of programming and less tolerance to data variability. With regard to the DCNNs, a large number of samples are needed for network training and the iterative optimization of parameters is partly a black-box operation [8].In the industrial applications, part defects in the samples can be easily identified with a picture by the classical computer vision method. Therefore, we do not need to feed the whole picture into the network for discrimination, which can reduce the number of features to be identified. As a result, the network is easier to converge. Therefore, by combining the classical image recognition method and DCNNs, the landing speed of deep learning technology in industrial applications can be effectively improved.In this work, an intelligent detection system that combined the classical computer vision method and DCNNs was designed to automatically detect the quality defects of micro-motor armatures. Firstly, the quality, excluding the region of copper wire crossing (ROC), is decided based on the classical computer vision technology. If the first result is positive, the ROC will be extracted and sent to the DCNNs for identification. If the result is still positive, the image is a defect-free sample, otherwise the whole image is labeled defective. In the experiments, this system works very fast and presen...

Polynomial edge reconstruction sensitivity, subpixel Sobel gradient kernel analysis

“…The proposed method will benefit search-based computer vision systems where hardware capabilities maybe limited and for enhanced preprocessing stages in machine learned edge detection. 34 For precise detection and tracking of characteristic edge features of nonrigid objects, particularly at the millimeter and micron scale; two types of implementation are identified. First, to estimate and refine edges gradient directions without prior knowledge of the sample boundary features.…”

Augmented classification for electrical coil winding defects

“…A common processing step that is a target for monitoring is the process of coil winding, assembly and terminations step of electrical machine manufacture. Early work by [16] considered the application of vision systems for stator faults (lamination gaps, mechanical damage etc), with a focus on the effect of illumination on detection and how it influences the practical introduction of the technology for this processing step. Similar work by [17] looked to combine more traditional computer vision methods with a deep convolutional neural network (CNN) for the automatic detection of defects within micro-motor armatures during their manufacture.…”

“…The introduction of automated and visual inspection systems capable of undertaking tasks often conducted by human operators has been of keen interest to researchers within electrical machine manufacture [16]. In many assembly tasks the control process is still done by operators on the shop floor where the final outcome is dependent on user skill, experience and decision making capabilities.…”

Research on Voltage Waveform Fault Detection of Miniature Vibration Motor Based on Improved WP-LSTM

“…Domestic manufacturers inspect the motors by observing the waveform of the oscilloscope with the naked eye to judge the quality of the motor. As shown in Figure 1 , manual inspection is slow, and the quality of the inspection cannot be guaranteed [ 2 , 3 ].…”